Triple
T34962307
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1989 NCAA Division I women's basketball championship |
E1008290
|
entity |
| Predicate | stateWithMostGamesHosted |
P197643
|
FINISHED |
| Object | Tennessee |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tennessee | Statement: [1989 NCAA Division I women's basketball championship, stateWithMostGamesHosted, Tennessee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateWithMostGamesHosted Context triple: [1989 NCAA Division I women's basketball championship, stateWithMostGamesHosted, Tennessee]
-
A.
worldSeriesGamesHosted
Indicates that the subject has hosted one or more World Series baseball games, with the object specifying which games or how many were hosted.
-
B.
numberOfOpenChampionshipsHosted
Indicates the count of Open Championship golf tournaments that have been hosted by a given entity.
-
C.
olympicGamesHosted
Indicates that a particular location or entity served as the host for a specific edition of the Olympic Games.
-
D.
holdsTournamentsIn
Indicates that an entity organizes or conducts tournaments at or within a specified location.
-
E.
cityOfGames
Indicates that a location is recognized as a major center or hub for games, gaming activities, or the games industry.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76dc69564819099e9e78aed6ff0a6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe9fb9735c8190a360b556c9d00b3f |
completed | May 9, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69fe9eaa88008190a9b2a469dc685002 |
completed | May 9, 2026, 2:40 a.m. |
| PDg | Predicate description generation | batch_69fe9fb88db08190a8f4af350633330e |
completed | May 9, 2026, 2:45 a.m. |
Created at: May 3, 2026, 4 p.m.